Simon Willison releases llm-meta-ai 0.2 with support for Muse Wonder
Version 0.2 of the llm-meta-ai plugin adds support for Muse Wonder. Simon Willison also shows its outputs at six reasoning effort levels, from minimal to max.
Simon Willison updated the llm-meta-ai plugin to version 0.2 and added support for Muse Wonder. Users of the plugin can now work with this model.
The author accompanies the release with examples of pelican drawings at six reasoning effort levels: minimal, low, medium, high, xhigh and max. These are specific examples of outputs; the article does not use them to establish the quality of the model across other tasks.
Why it matters
Support in an existing plugin allows its users to try Muse Wonder. Examples at different reasoning settings provide a basis for making your own comparisons, not proof of which setting will be best for a particular task.
Release card
Muse Wonder
Meta AI
- Availability
- The model can be used through version 0.2 of the llm-meta-ai plugin.
- Creating pelican drawings at different reasoning effort levels.
According to the article, Artificial Analysis rates Muse Wonder at the max reasoning effort level as equivalent to GPT-6.1 Sol. The author also compares pelican drawings with outputs from Muse 1.3 and Muse 1.2 and describes the improvement on this specific task as substantial.
The card summarizes information from the article and any dated corrections, with a link to the original source. It is not our assessment of the model. It does not yet have a dedicated editorial profile. Model selection and other announcements →
Relevant practical impact
What this means
For individuals
If you use the llm-meta-ai plugin, version 0.2 adds Muse Wonder to the available model selection.
Check the original
Event sources
only one source so far · 1 publisher, 1 independent. We count feeds from the same owner only once.